Agent: CursorLLM: Claude 3.5#llm-infrastructure#kubernetes#routing#inference-optimization#gateway-api
llm-d Router is a production-grade intelligent entry point for LLM inference traffic. It provides KV-cache aware routing, request prioritization, and advanced flow control across diverse request formats. The router integrates with L7 proxies via Envoy's ext-proc protocol and supports both standalone and Kubernetes Gateway API deployment models for optimized LLM serving.